What moves, and what does not.
What the system takes over
- Screening literature: collecting everything new in a defined field and sorting it by relevance to a stated question
- Cleaning up a reference library: removing duplicates, repairing details, checking every reference against its official record
- Reformatting a publication list into DFG, ERC, NSF, Europass or a university’s house structure
- Keeping the reusable proposal text current and reshaping it to a call’s structure and page limits
- Tracking calls, Zwischenberichte, Abschlussberichte, review commitments and exam dates
- Keeping the supervision record for each doctoral candidate
- Checking appointment applications for completeness against the published formal criteria
- Keeping the reproducibility record: which data, which version of the analysis, which figure
What stays with you
- The research question. The hypothesis. The interpretation
- Whether a result means anything
- The assessment of a person — in a reference, a viva, a Berufungsverfahren
- What to review, and what a review concludes
What we build
The proposal core
One maintained store: the CV in every format ever demanded, the publication list, the group description, infrastructure, the preliminary-work paragraphs for each research line with their figures and citations, past project outcomes, the data management plan template, the equal opportunity measures. Every item dated and sourced. About two weeks to build, mostly pulling text out of three old proposals, and it is the last time those paragraphs are ever written from nothing.
The proposal skeleton
You give it a call’s structure, headings and page limits. Out comes a skeleton with the core material already placed at roughly the right length, and every section that needs original thought left empty and labelled. Five weeks becomes about ten days, and almost all ten go into the work programme — the part that gets funded.
The supervision record
One private file per doctoral candidate: what was agreed, what happened, milestones against the Betreuungsvereinbarung, obstacles raised. Ninety seconds of dictation after each meeting. The piece we would install first if we could install only one — because meetings currently begin with both people trying to remember, reference letters two years later are written from a blank page, and when a candidate is quietly in trouble the record shows it four months before anyone notices in conversation.
The literature screen
For candidates: six hundred abstracts checked against inclusion and exclusion criteria that are written down first. Every decision recorded with the criterion that produced it, every borderline case flagged for you. For systematic reviews this follows PRISMA and produces the flow-diagram numbers as a by-product.
The reproducibility record
Which data, which version of the analysis, which software setup, which output. Every figure carries the exact command that made it. Set up in an afternoon in year one, and worth a month in year four.
Where it stops
It never generates a citation, and never summarises a paper you will cite.
Read more
Citations come from your reference manager and are checked against each paper’s official record. Nothing that produces prose is allowed to produce a reference, ever, under any framing. Invented references are the most common and most destructive failure of language models in research, and a tired author at 23:00 cannot spot them because they look exactly right. Screening a thousand abstracts to find forty papers is routine work; reading those forty is the job — so the screen gives you titles, abstracts and links, never a summary presented as good enough.
No manuscript under review touches an external service: peer review is confidential and a manuscript is unpublished work belonging to someone else. The system never writes the argument, the hypothesis or the interpretation. It never ranks candidates in an appointment procedure — a Berufungsverfahren is legally reviewable, documented, and subject to the AGG; we have refused this twice. No data is invented, no figure generated, and no cleaning happens silently: raw stays raw. Every engagement ends with a one-page document you keep, naming which tasks used an AI tool and which funder and publisher disclosure rules apply.
How you see it working
Days from a call’s announcement to a submitted proposal: typically five weeks down to about ten working days. Proposals submitted per year. Supervision meetings with a written record: from occasional to all of them. Figures reproducible with a single command: all of them. And the only one anybody cares about — hours per week available for research, which for both professors went from close to zero to between eight and twelve.
What it asks of you, and when we say no.
What it asks of you
Two weeks of pulling text out of old proposals to build the core, once. Ninety seconds of dictation after each supervision meeting. And the discipline of reading the forty papers the screen found, which was always the job.
When we say no
When someone wants a paper generator — asked twice, phrased as "a first draft of the introduction" and "just the related work section". The related work section is where you show you have read the field. Also when a department wants per-person publication metrics, which is surveillance in a bibliometric costume. And when a doctoral candidate needs a supervisor rather than a system, which is the saddest version.
What clients say
Sixty per cent of every proposal already existed, in three earlier proposals, in slightly the wrong format, and I retyped it every March because finding it felt harder. Two weeks of extraction and I have not written those pages from nothing since. A DFG submission that took five weeks now takes about ten working days and nearly all of those days go to the work programme, which is the part that gets funded. He would not let anything generate a citation — references resolve by DOI or they do not appear — and given what I have seen happen to colleagues, that rule is the reason I let him near any of it.
Year three, nine hundred unread PDFs, three chapters that no longer agreed with each other, and forty minutes with my supervisor every six weeks. The screening pipeline got six hundred abstracts down to the forty I actually had to read, and it recorded which criterion produced every decision. The reproducibility setup took an afternoon and I now know which script version made which figure, which I understand is a boring sentence and it saved me in my defence. He also told me, kindly, that what I really needed was a supervisor, and he was right.
Tell us what you are dealing with.
Thirty minutes, free, no preparation. We tell you honestly where AI could change something for you, and where it would not.